Upload README.md with huggingface_hub

README.md

@@ -1,18 +1,11 @@
 ---
 quantized_by: bartowski
 pipeline_tag: text-generation
-language:
-- zh
-- en
-base_model_relation: quantized
-license: mit
-base_model: THUDM/GLM-4-32B-0414
-extra_gated_prompt: "This model is currently broken, see more here: https://github.com/ggml-org/llama.cpp/pull/12957.\n\nI don't want your data, but this is the only way to leave the model up while preventing accidental downloads."
 ---
 
 ## Llamacpp imatrix Quantizations of GLM-4-32B-0414 by THUDM
 
-Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5132">b5132</a> for quantization.
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5173">b5173</a> for quantization.
 
 Original model: https://huggingface.co/THUDM/GLM-4-32B-0414
 
@@ -30,6 +23,10 @@ Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or a
 {prompt}<|assistant|>
 ```
 
+## What's new:
+
+Brings fixes from https://github.com/ggml-org/llama.cpp/pull/13021
+
 ## Download a file (not the whole branch) from below:
 
 | Filename | Quant type | File Size | Split | Description |